Stars
ThinkGen: Generalized Thinking for Visual Generation
An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution
Official inference repo for FLUX.2 models
CogView4, CogView3-Plus and CogView3(ECCV 2024)
This is the official code of AAAI 2025: RetouchGPT: LLM-based Interactive High-Fidelity Face Retouching via Imperfection Prompting.
(CVPR 2025) Adversarial Diffusion Compression for Real-World Image Super-Resolution [PyTorch]
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment
👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
Tiny AutoEncoder for Stable Diffusion (and other image models)
[CVPR 2025] Official code repository for "Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach"
[AAAI2025] This is the official PyTorch codes for the paper: "FaceMe: Robust Blind Face Restoration With Personal Identification"
[ECCV 2024] OMG: Occlusion-friendly Personalized Multi-concept Generation In Diffusion Models
[NeurIPS 2024] SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models
Repository for "WaveFace: Authentic Face Restoration with Efficient Frequency Recovery" (CVPR24)
Official Repo for CVPR 2025 paper "OSDFace: One-Step Diffusion Model for Face Restoration"
(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis
Official code for our Paper "SSL: A Self-similarity Loss for Improving Generative Image Super-resolution" in ACMMM 2024